Fix workspace overflow for (*ACCEPT) with deeply nested parentheses.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1631 2f5784b3-3f2a-0410-8824-cb99058d5e15

8 files changed, 53 insertions, 22 deletions

diff --git a/ChangeLog b/ChangeLog
index 106ab35..205e2ca 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -7,17 +7,17 @@ development is happening in the PCRE2 10.xx series.
 Version 8.39 xx-xxxxxx-201x
 ---------------------------
 
-1.  If PCRE_AUTO_CALLOUT was set on a pattern that had a (?# comment between 
-    an item and its qualifier (for example, A(?#comment)?B) pcre_compile() 
+1.  If PCRE_AUTO_CALLOUT was set on a pattern that had a (?# comment between
+    an item and its qualifier (for example, A(?#comment)?B) pcre_compile()
     misbehaved. This bug was found by the LLVM fuzzer.
-    
+
 2.  Similar to the above, if an isolated \E was present between an item and its
     qualifier when PCRE_AUTO_CALLOUT was set, pcre_compile() misbehaved. This
     bug was found by the LLVM fuzzer.
 
-3.  Further to 8.38/46, negated classes such as [^[:^ascii:]\d] were also not 
+3.  Further to 8.38/46, negated classes such as [^[:^ascii:]\d] were also not
     working correctly in UCP mode.
-    
+
 4.  The POSIX wrapper function regexec() crashed if the option REG_STARTEND
     was set when the pmatch argument was NULL. It now returns REG_INVARG.
 
@@ -26,30 +26,34 @@ Version 8.39 xx-xxxxxx-201x
 6.  An empty \Q\E sequence between an item and its qualifier caused
     pcre_compile() to misbehave when auto callouts were enabled. This bug was
     found by the LLVM fuzzer.
-    
-7.  If a pattern that was compiled with PCRE_EXTENDED started with white 
-    space or a #-type comment that was followed by (?-x), which turns off 
+
+7.  If a pattern that was compiled with PCRE_EXTENDED started with white
+    space or a #-type comment that was followed by (?-x), which turns off
     PCRE_EXTENDED, and there was no subsequent (?x) to turn it on again,
     pcre_compile() assumed that (?-x) applied to the whole pattern and
     consequently mis-compiled it. This bug was found by the LLVM fuzzer.
-    
+
 8.  An call of pcre_copy_named_substring() for a named substring whose number
     was greater than the space in the ovector could cause a crash.
-    
+
 9.  Yet another buffer overflow bug involved duplicate named groups with a
     group that reset capture numbers (compare 8.38/7 below). Once again, I have
     just allowed for more memory, even if not needed. (A proper fix is
     implemented in PCRE2, but it involves a lot of refactoring.)
-    
-10. pcre_get_substring_list() crashed if the use of \K in a match caused the 
-    start of the match to be earlier than the end. 
+
+10. pcre_get_substring_list() crashed if the use of \K in a match caused the
+    start of the match to be earlier than the end.
 
 11. Migrating appropriate PCRE2 JIT improvements to PCRE.
 
 12. A pattern such as /(?<=((?C)0))/, which has a callout inside a lookbehind
-    assertion, caused pcretest to generate incorrect output, and also to read 
+    assertion, caused pcretest to generate incorrect output, and also to read
     uninitialized memory (detected by ASAN or valgrind).
 
+13. A pattern that included (*ACCEPT) in the middle of a sufficiently deeply
+    nested set of parentheses of sufficient size caused an overflow of the
+    compiling workspace (which was diagnosed, but of course is not desirable).
+
 
 Version 8.38 23-November-2015
 -----------------------------
diff --git a/pcre_compile.c b/pcre_compile.c
index b9a239e..5019854 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2014 University of Cambridge
+           Copyright (c) 1997-2016 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -560,6 +560,7 @@ static const char error_texts[] =
   /* 85 */
   "parentheses are too deeply nested (stack check)\0"
   "digits missing in \\x{} or \\o{}\0"
+  "regular expression is too complicated\0"
   ;
 
 /* Table to identify digits and hex digits. This is used when compiling
@@ -4591,7 +4592,8 @@ for (;; ptr++)
     if (code > cd->start_workspace + cd->workspace_size -
         WORK_SIZE_SAFETY_MARGIN)                       /* Check for overrun */
       {
-      *errorcodeptr = ERR52;
+      *errorcodeptr = (code >= cd->start_workspace + cd->workspace_size)?
+        ERR52 : ERR87;
       goto FAILED;
       }
 
@@ -6626,8 +6628,21 @@ for (;; ptr++)
             cd->had_accept = TRUE;
             for (oc = cd->open_caps; oc != NULL; oc = oc->next)
               {
-              *code++ = OP_CLOSE;
-              PUT2INC(code, 0, oc->number);
+              if (lengthptr != NULL)
+                {
+#ifdef COMPILE_PCRE8
+                *lengthptr += 1 + IMM2_SIZE;
+#elif defined COMPILE_PCRE16
+                *lengthptr += 2 + IMM2_SIZE;
+#elif defined COMPILE_PCRE32
+                *lengthptr += 4 + IMM2_SIZE;
+#endif
+                }
+              else
+                {
+                *code++ = OP_CLOSE;
+                PUT2INC(code, 0, oc->number);
+                }
               }
             setverb = *code++ =
               (cd->assert_depth > 0)? OP_ASSERT_ACCEPT : OP_ACCEPT;
diff --git a/pcre_internal.h b/pcre_internal.h
index f7a5ee7..dbfe80e 100644
--- a/pcre_internal.h
+++ b/pcre_internal.h
@@ -7,7 +7,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2014 University of Cambridge
+           Copyright (c) 1997-2016 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -2289,7 +2289,7 @@ enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,  ERR5,  ERR6,  ERR7,  ERR8,  ERR9,
        ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59,
        ERR60, ERR61, ERR62, ERR63, ERR64, ERR65, ERR66, ERR67, ERR68, ERR69,
        ERR70, ERR71, ERR72, ERR73, ERR74, ERR75, ERR76, ERR77, ERR78, ERR79,
-       ERR80, ERR81, ERR82, ERR83, ERR84, ERR85, ERR86, ERRCOUNT };
+       ERR80, ERR81, ERR82, ERR83, ERR84, ERR85, ERR86, ERR87, ERRCOUNT };
 
 /* JIT compiling modes. The function list is indexed by them. */
 
diff --git a/pcreposix.c b/pcreposix.c
index dcc13ef..55b6ddc 100644
--- a/pcreposix.c
+++ b/pcreposix.c
@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2014 University of Cambridge
+           Copyright (c) 1997-2016 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -173,7 +173,8 @@ static const int eint[] = {
   REG_BADPAT,  /* group name must start with a non-digit */
   /* 85 */
   REG_BADPAT,  /* parentheses too deeply nested (stack check) */
-  REG_BADPAT   /* missing digits in \x{} or \o{} */
+  REG_BADPAT,  /* missing digits in \x{} or \o{} */
+  REG_BADPAT   /* pattern too complicated */
 };
 
 /* Table of texts corresponding to POSIX error codes */
diff --git a/testdata/testinput11 b/testdata/testinput11
index ac9d228..6f0989a 100644
--- a/testdata/testinput11
+++ b/testdata/testinput11
@@ -138,4 +138,6 @@ is required for these tests. --/
 
 /.((?2)(?R)\1)()/B
 
+/([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00](*ACCEPT)/
+
 /-- End of testinput11 --/
diff --git a/testdata/testoutput11-16 b/testdata/testoutput11-16
index 280692e..3c485da 100644
--- a/testdata/testoutput11-16
+++ b/testdata/testoutput11-16
@@ -765,4 +765,7 @@ Memory allocation (code space): 14
  25     End
 ------------------------------------------------------------------
 
+/([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00](*ACCEPT)/
+Failed: regular expression is too complicated at offset 490
+
 /-- End of testinput11 --/
diff --git a/testdata/testoutput11-32 b/testdata/testoutput11-32
index cdbda74..e19518d 100644
--- a/testdata/testoutput11-32
+++ b/testdata/testoutput11-32
@@ -765,4 +765,7 @@ Memory allocation (code space): 28
  25     End
 ------------------------------------------------------------------
 
+/([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00](*ACCEPT)/
+Failed: missing ) at offset 509
+
 /-- End of testinput11 --/
diff --git a/testdata/testoutput11-8 b/testdata/testoutput11-8
index cb37896..5a4fbb2 100644
--- a/testdata/testoutput11-8
+++ b/testdata/testoutput11-8
@@ -765,4 +765,7 @@ Memory allocation (code space): 10
  38     End
 ------------------------------------------------------------------
 
+/([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00]([00](*ACCEPT)/
+Failed: missing ) at offset 509
+
 /-- End of testinput11 --/